Triple

T22055272
Position Surface form Disambiguated ID Type / Status
Subject Battle of the Ancre (1916) E544991 entity
Predicate place P373 FINISHED
Object Somme NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Somme | Statement: [Battle of the Ancre (1916), place, Somme]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Somme
Context triple: [Battle of the Ancre (1916), place, Somme]
  • A. Ham, Somme
    Ham, Somme is a commune in northern France located in the Somme department within the Hauts-de-France region.
  • B. Somme River chosen
    The Somme River is a waterway in northern France that became historically significant as the site of one of World War I’s largest and bloodiest battles.
  • C. Verdun
    Verdun is a borough of Montreal, Quebec, known for its historic waterfront along the St. Lawrence River and its mix of residential neighborhoods and urban amenities.
  • D. Verdun
    Verdun is a tram stop on the Tramway de Tours network in the city of Tours, France.
  • E. Yser Front
    The Yser Front was a key World War I defensive line in western Belgium where Belgian forces halted the German advance along the Yser River.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e11e3377c48190890c17407b9527d6 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1285790948190b21abfb09abbb5e5 completed April 28, 2026, 9:36 p.m.
Created at: April 16, 2026, 8:26 p.m.